© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62003
    Prev
    Next
    INDEX
    Explanations

    brands and product lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľĶ
    -0.11
    ë¡Ŀ
    -0.11
    èĢģ人家
    -0.10
    åĮ¾
    -0.10
    /lists
    -0.10
    俱
    -0.09
    ä½ľä¸ºä¸Ģç§į
    -0.09
    æijŀ
    -0.09
    æĮ¹
    -0.08
    åıªæĺ¯ä¸Ģ个
    -0.08
    POSITIVE LOGITS
    ãģ®ãģ«
    0.09
    æݨåĩºçļĦ
    0.09
    æ±īåŃIJ
    0.09
    ä¾Ŀæīĺ
    0.08
    ç§ijå°Ķ
    0.08
    åŁºäºİ
    0.08
    éĤ£è¾¹
    0.08
    rys
    0.08
    ×ķף
    0.08
    [section
    0.08
    Activations Density 0.109%

    No Known Activations